© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10260
    Prev
    Next
    INDEX
    Explanations

    phrases related to the position of "running back" in American football

    oai_token-act-pair · gpt-3.5-turbo

    references to "running backs" in football contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alam
    -0.77
    opol
    -0.76
    NetMessage
    -0.73
    olia
    -0.73
    ango
    -0.73
     plur
    -0.72
    IFIED
    -0.71
    ulin
    -0.69
    obyl
    -0.68
    hap
    -0.68
    POSITIVE LOGITS
     backs
    1.00
     mate
    0.97
     coach
    0.86
     mates
    0.84
    back
    0.82
    backs
    0.79
     af
    0.73
     downhill
    0.72
    aways
    0.71
    ames
    0.71
    Activations Density 0.039%

    No Known Activations